Abstract
Simultaneous localization and mapping (SLAM) is the crucial prerequisite for mobile robots to accomplish autonomy. In this paper, PSO-UFastSLAM based on the unscented-FastSLAM (UFastSLAM) and the particle swarm optimization (PSO) is proposed. The UFastSLAM combines unscented particle filter (UPF) and unscented Kalman filter (UKF) to estimate the robot poses and features. Furthermore, to prevent the particles degeneracy and impoverishment, PSO is adapted to optimize particles. The proposed method is applied on our own research platform, autonomous underwater vehicle (AUV), through sea trials in Tuandao Bay. The results of simulation and sea trial reveal that PSO-UFastSLAM has better accuracy and effectiveness in terms of estimation of robot and features while compared with UFastSLAM and standard FastSLAM.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
